AI RESEARCH
Topology-Preserving Deep Joint Source-Channel Coding for Semantic Communication
arXiv CS.LG
•
ArXi:2603.17126v1 Announce Type: new Many wireless vision applications, such as autonomous driving, require preservation of global structural information rather than only per-pixel fidelity. However, existing Deep joint source-channel coding (DeepJSCC) schemes mainly optimize pixel-wise losses and provide no explicit protection of connectivity or topology. This letter proposes TopoJSCC, a topology-aware DeepJSCC framework that integrates persistent-homology regularizers to end-to-end